Reconstruction and Empirical Research on Full-Process Maritime English Teaching in Higher Vocational Colleges Supported by Dual Collaborative Generative AI Models
DOI:
https://doi.org/10.54097/d28kdm66Keywords:
Generative Artificial Intelligence, Maritime English in Higher Vocational Colleges, Dual-Model Collaboration, Full-Process Teaching Empirical ResearchAbstract
Maritime English teaching in higher vocational colleges is plagued by practical dilemmas including insufficient provision of occupation-based scenarios, limited oral training channels, unimplemented student stratification, and rigid summative assessment systems. To advance the digital transformation of maritime specialized English education, this study adopts situated learning, task-based language teaching, and multi-dimensional process evaluation theories to construct a three-stage full-process teaching framework featuring the collaborative operation of DeepSeek and Doubao. The framework forms a closed-loop teaching system of "pre-class differentiated guided learning – in-class situated interactive training – post-class data-driven assessment". This research aims to develop a low-cost, replicable digital teaching implementation scheme, providing a localized practical paradigm for the intelligent teaching reform of English for Specific Purposes (ESP) in higher vocational education.
Downloads
References
[1] Wang, H. X. (2024). Digital transformation path of ESP courses in higher vocational education from the perspective of smart education. Chinese Vocational and Technical Education, (28), 62–68.
[2] Dong, J. W. (2025). Practical dilemmas and countermeasures of maritime English teaching in higher vocational colleges. Times Characters, (30), 175–176.
[3] Wang, S. R. (2025). Restructuring vocational-oriented English teaching in higher vocational colleges in the new era. Foreign Language World, (01), 41–47.
[4] Wang, J. (2025). An analysis of integrating maritime vocational safety culture into higher vocational English teaching from the perspective of AIGC. Pearl River Water Transport, (10), 106–108.
[5] Zhang, Y. X. (2025). The 321 teaching model of generative AI in marine engineering English writing. Overseas English, (22), 112–115.
[6] Mohamed, A. (2025). AI-generated maritime English training materials for seafarers. Maritime Education, 19(2), 76–92.
[7] Godwin-Jones, R. (2024). Distributed agency in second language learning and teaching through generative AI. Language Learning & Technology, 28(2), 5–30.
[8] Kukulska-Hulme, A. (2024). Mobile language learning: Reflecting on the past and envisioning the future. In (Book Title Editor) Theory and practice in vocabulary research in digital environments. Routledge.
[9] Hockley, T. (2024). Generative AI and digital divide in EFL teaching. ELT Journal, 78(4), 478–485.
[10] Li, Y., & Zhao, C. Y. (2022). Blended teaching practice of maritime English based on OBE concept. Maritime Education Research, (04), 67–71.
[11] Zhuo, Y. Q. (2025). Design of outcome-oriented role-play teaching method for maritime English. Maritime Education Research, (04), 43–47.
[12] Li, M. (2025). Risks and balancing paths of generative AI hallucinations in foreign language teaching. Computer-Assisted Foreign Language Education, (02), 18–25.
[13] Chen, X. (2024). LLM-assisted differentiated adaptation strategies for higher vocational English from the perspective of digital literacy divide. Modern Foreign Languages, (06), 821–830.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 International Journal of Education and Humanities
This work is licensed under a Creative Commons Attribution 4.0 International License.
